fix(import): stop a generic bank signature from claiming, and misreading, a richer file

Review finding on #330, two defects with one root cause.

Desjardins' fingerprint is date/description/montant/solde — four labels any
Canadian bank could emit — and MIN_SIGNATURE_LABELS = 4 did not deliver the
property it promised, because matching was by SUBSET. Any
Date;Description;Montant;Solde file was announced 'Format Desjardins reconnu'.
A variant built only from generic labels must now describe the header exactly;
one carrying a discriminating label (chequenumber, categorie, memo) keeps
subset matching, so extra columns stay fine once something identifies the bank.

Worse, a matched signature's single amount column short-circuited the
sparse-complementary scan instead of being arbitrated against it. A
Date;Description;Debit;Credit;Montant;Solde file reads correctly as debit/credit
before #330 and became one unsigned column after, importing every deposit as an
expense. The scan now runs first; a signature's amount column only wins when the
pair contains it — which is what RBC's genuine Cheque Number / CAD$ case needs,
and it still passes.

Refs #330

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

src/utils/bankSignatures.test.ts

@@ -222,21 +222,90 @@ describe("what the signatures actually buy (#330)", () => {
     expect(configOf(readCsvFixture("bank-rbc")).amountMode).toBe("single");
   });
 
-  it("keeps Tangerine's direction column out of the description", () => {
+  it("keeps Tangerine's direction column out of the description, signature or not", () => {
     // `Transaction` is a description keyword of the generic dictionary, and
     // Tangerine's `Transaction` column holds DEBIT / CREDIT. Read as the
     // description, every transaction of the file is labelled `DEBIT`.
+    //
+    // This used to be rescued by the Tangerine signature alone, leaving any
+    // unrecognised file with a `Transaction` column broken. The cardinality
+    // veto in `detectDescriptionColumn` fixes the cause instead: a labelled
+    // column that behaves like an enum is not the description, whether or not a
+    // bank was identified.
     const anonymised = withHeader(
       readCsvFixture("bank-tangerine"),
       "Date,Transaction,Nom,Note,Montant"
     );
     expect(bankOf(anonymised)).toBeNull();
-    expect(configOf(anonymised).columnMapping.description).toBe(1);
+    expect(configOf(anonymised).columnMapping.description).toBe(2);
 
     expect(configOf(readCsvFixture("bank-tangerine")).columnMapping.description).toBe(
       2
     );
   });
+
+  it("does not let a generic variant claim a richer header", () => {
+    // Review finding on #340: Desjardins' fingerprint is four labels any
+    // Canadian bank could emit, so matching them as a SUBSET announced
+    // "Format Desjardins reconnu" over files that have nothing to do with it.
+    // A variant made only of generic labels now has to describe the header
+    // exactly.
+    const richer =
+      "Date;Description;Débit;Crédit;Montant;Solde\n" +
+      "05/01/2025;EPICERIE;84,32;;-84,32;1000,00\n" +
+      "15/01/2025;DEPOT PAIE;;1250,00;1250,00;2250,00\n" +
+      "20/01/2025;LOYER;900,00;;-900,00;1350,00\n" +
+      "25/01/2025;REMBOURSEMENT;;45,00;45,00;1395,00\n";
+    expect(bankOf(richer)).toBeNull();
+
+    // The exact header still is Desjardins.
+    const exact =
+      "Date;Description;Montant;Solde\n" +
+      "05/01/2025;EPICERIE;-84,32;1000,00\n" +
+      "15/01/2025;DEPOT PAIE;1250,00;2250,00\n";
+    expect(bankOf(exact)).toBe("desjardins");
+  });
+
+  it("does not let a signature's amount column displace a pair it is not in", () => {
+    // The measured regression: with the false Desjardins match above, the
+    // signature's `Montant` short-circuited the sparse-complementary scan, so a
+    // file that reads correctly as debit/credit became one unsigned column and
+    // every deposit imported as an expense. The scan now runs first and the
+    // signature only wins when the pair contains its column — which is what
+    // RBC's genuine `Cheque Number` / `CAD$` case needs.
+    const richer =
+      "Date;Description;Débit;Crédit;Montant;Solde\n" +
+      "05/01/2025;EPICERIE;84,32;;-84,32;1000,00\n" +
+      "15/01/2025;DEPOT PAIE;;1250,00;1250,00;2250,00\n" +
+      "20/01/2025;LOYER;900,00;;-900,00;1350,00\n" +
+      "25/01/2025;REMBOURSEMENT;;45,00;45,00;1395,00\n";
+    const config = configOf(richer);
+    expect(config.amountMode).toBe("debit_credit");
+    expect(config.columnMapping.debitAmount).toBe(2);
+    expect(config.columnMapping.creditAmount).toBe(3);
+
+    // RBC keeps its override: there the declared amount column IS in the pair.
+    expect(configOf(readCsvFixture("bank-rbc")).amountMode).toBe("single");
+  });
+
+  it("holds even for a legitimately recognised bank whose file grew columns", () => {
+    // The guard above is only reachable through a signature that really matches,
+    // so it needs a discriminating one. Tangerine is identified by `memo`, so it
+    // still matches as a subset when the export gains Débit/Crédit columns — and
+    // then its declared `Amount` must not displace that genuine pair either.
+    const grown =
+      "Date,Transaction,Name,Memo,Amount,Débit,Crédit\n" +
+      "05/01/2025,DEBIT,EPICERIE METRO,,-84.32,84.32,\n" +
+      "15/01/2025,CREDIT,DEPOT PAIE,Paie,1250.00,,1250.00\n" +
+      "20/01/2025,DEBIT,LOYER,,-900.00,900.00,\n" +
+      "25/01/2025,CREDIT,REMBOURSEMENT,,45.00,,45.00\n";
+    expect(bankOf(grown)).toBe("tangerine");
+
+    const config = configOf(grown);
+    expect(config.amountMode).toBe("debit_credit");
+    expect(config.columnMapping.debitAmount).toBe(5);
+    expect(config.columnMapping.creditAmount).toBe(6);
+  });
 });
 
 describe("an unknown file falls back to the generic dictionary (#330)", () => {

src/utils/bankSignatures.ts

@@ -85,6 +85,30 @@ export interface BankSignature {
  */
 export const MIN_SIGNATURE_LABELS = 4;
 
+/**
+ * Labels any Canadian bank could emit. A variant built only from these
+ * identifies no bank in particular, so the count alone does not deliver the
+ * property `MIN_SIGNATURE_LABELS` promises — such a variant has to match the
+ * header exactly (see `matchBankSignature`).
+ */
+const GENERIC_LABELS: ReadonlySet<string> = new Set([
+  "date",
+  "description",
+  "libelle",
+  "detail",
+  "transaction",
+  "montant",
+  "amount",
+  "solde",
+  "balance",
+  "debit",
+  "credit",
+  "retrait",
+  "depot",
+  "withdrawal",
+  "deposit",
+]);
+
 /**
  * The table. Written from the banks' documented export layouts; none of it has
  * been verified against a real statement (see the file header). Adding a bank
@@ -288,6 +312,20 @@ export function matchBankSignature(
 
     for (const variant of signature.variants) {
       if (!variant.labels.every((label) => index.has(label))) continue;
+      // A variant made only of generic labels must describe the header EXACTLY,
+      // not merely be contained in it. Desjardins is
+      // `date;description;montant;solde` — four labels any Canadian bank could
+      // emit — so accepting them as a SUBSET let a
+      // `Date;Description;Débit;Crédit;Montant;Solde` file claim to be
+      // Desjardins. A variant carrying a discriminating label (`chequenumber`,
+      // `categorie`, `memo`, …) keeps subset matching: extra columns are fine
+      // once something actually identifies the bank.
+      if (
+        variant.labels.every((label) => GENERIC_LABELS.has(label)) &&
+        index.size !== variant.labels.length
+      ) {
+        continue;
+      }
       return { signature, variant, roles: rolesOf(variant, index) };
     }
   }